Fault diagnosis of output‐related processes with multi‐block MOPLS

Abstract

For fault diagnosis of output‐related processes, a relatively high false alarm rate (FAR) of output‐irrelevant faults exists because the output‐irrelevant variables are not removed completely by conventional approaches. A relatively large number of computational loads is thus required. Therefore, in this paper, a new fault diagnosis approach based on multiblock modified orthogonal projections to latent structures is proposed to complete fault diagnosis for complex chemical processes, particularly for the penicillin fermentation process. The main contributions are as follows: (1) Multiblock orthogonal projections to latent structures are applied to remove the noncorrelated variables of input blocks, which requires a relatively low computational load. In addition, block scores are obtained by block weights rather than super weights to better describe the character of each subblock. (2) Complete orthogonal decomposition between input block variables and output is explored to completely separate output‐related and output‐irrelevant variables to improve the accuracy of diagnosis. (3) A hierarchical diagnosis scheme, which is composed of block monitoring statistics and subblock monitoring statistics, is proposed to monitor and localize faults. Penicillin fermentation process is considered in this study, and the penicillin concentration‐relevant fault in each block and subblock is analyzed. The results of this study show that the proposed method has steadier performance on output‐related fault diagnoses and diagnoses faults more accurately.

Large-Scale Supervised Process Monitoring Based on Distributed Modified Principal Component Regression

“…Therefore, quality-related fault detection is really necessary for industrial processes. Recently, with the rapid development of sensor and computer technology, many research results have been achieved in the field of data-driven process monitoring in which quality-related multivariate statistical process monitoring (MSPM) methods have been studied widely. , Partial least squares (PLS) is the most common quality-related monitoring method in the MSPM field, which combines the process variables matrix and quality variables matrix of industrial processes to extract the main components and builds the regression model, in order to improve the performance of process monitoring and accurately detect quality-related faults. Many modified PLS methods have been proposed in recent years.…”

Fault monitoring based on locally weighted probabilistic kernel partial least square for nonlinear time‐varying processes

“…The study on fault diagnosis is a very important assignment and has been widely researched over the past several decades. By far, in the field of fault diagnosis, data‐driven methods have recently become very popular and have been successfully used in many industrial processes, such as petroleum, chemical, metallurgical, food and other industries . Some representative data‐based fault diagnosis methods including principal component analysis (PCA), partial least squares (PLS), independent component analysis (ICA), artificial neural networks (ANN), and Bayesian methods have been proposed for process fault detection and diagnosis.…”